© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15654
    Prev
    Next
    INDEX
    Explanations

    derivatives and gradients

    np_acts-logits-general · gemini-2.5-flash-lite

    calculus, derivatives, and gradients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused33>
    0.58
     यून
    0.56
     фестива
    0.55
     বিজয়
    0.53
    য়েছে
    0.53
    铯
    0.53
     ओलंपिक
    0.52
     الاجتماعي
    0.52
    🌃
    0.52
     लाह
    0.52
    POSITIVE LOGITS
     derivative
    1.09
     Derivative
    0.97
     derivatives
    0.93
     deriv
    0.89
     Derivatives
    0.89
     differentiable
    0.83
    Derivative
    0.79
    derivative
    0.78
     dériv
    0.75
    deriv
    0.75
    Activations Density 0.007%

    No Known Activations